Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    1.54
    （
    1.05
    ((
    0.99
    /
    0.93
    هم
    0.91
     (
    0.91
    (_,
    0.91
    ها
    0.90
    (,
    0.89
    ла
    0.86
    POSITIVE LOGITS
     along
    1.49
     which
    1.45
     alongside
    1.35
     oraz
    1.34
     throughout
    1.26
    which
    1.24
     spearheaded
    1.22
     during
    1.21
     która
    1.21
     amidst
    1.21
    Act Density 0.454%

    No Known Activations